© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12610
    Prev
    Next
    INDEX
    Explanations

    HTML or XML code snippets and code-related terms like functions, spinner, error messages, and variable assignments, along with some formatting tags and bracketed expressions, possibly including citations and references with numbers

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    landt
    -0.60
     EconPapers
    -0.57
     يتيمه
    -0.56
    sidemargin
    -0.56
    :✨
    -0.55
    tagHelperRunner
    -0.55
    fjspx
    -0.54
     Progressive
    -0.54
    RTEX
    -0.53
    Progressive
    -0.52
    POSITIVE LOGITS
    Fazit
    0.53
    UrlResolution
    0.53
    таратура
    0.52
    ::::::::::::::::
    0.49
     TextAlign
    0.49
    photographer
    0.48
     препратки
    0.48
    OrWhiteSpace
    0.48
    zyła
    0.48
     RemoteException
    0.48
    Activations Density 3.527%

    No Known Activations